sanchit-gandhi HF staff commited on
Commit
1e26c57
1 Parent(s): c5a5891

End of training

Browse files
Files changed (4) hide show
  1. README.md +2 -1
  2. all_results.json +7 -0
  3. train_results.json +7 -0
  4. trainer_state.json +630 -0
README.md CHANGED
@@ -2,6 +2,7 @@
2
  license: cc-by-nc-4.0
3
  base_model: facebook/mms-lid-126
4
  tags:
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: mms-lid-ft-mix
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # mms-lid-ft-mix
15
 
16
- This model is a fine-tuned version of [facebook/mms-lid-126](https://huggingface.co/facebook/mms-lid-126) on the None dataset.
17
 
18
  ## Model description
19
 
 
2
  license: cc-by-nc-4.0
3
  base_model: facebook/mms-lid-126
4
  tags:
5
+ - audio-classification
6
  - generated_from_trainer
7
  model-index:
8
  - name: mms-lid-ft-mix
 
14
 
15
  # mms-lid-ft-mix
16
 
17
+ This model is a fine-tuned version of [facebook/mms-lid-126](https://huggingface.co/facebook/mms-lid-126) on the sanchit-gandhi/vctk dataset.
18
 
19
  ## Model description
20
 
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.95,
3
+ "train_loss": 0.4612073403596878,
4
+ "train_runtime": 4968.0781,
5
+ "train_samples_per_second": 6.441,
6
+ "train_steps_per_second": 0.201
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.95,
3
+ "train_loss": 0.4612073403596878,
4
+ "train_runtime": 4968.0781,
5
+ "train_samples_per_second": 6.441,
6
+ "train_steps_per_second": 0.201
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,630 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9525691699604746,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1.8e-05,
14
+ "loss": 3.0593,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "learning_rate": 3.6e-05,
20
+ "loss": 1.6864,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.12,
25
+ "learning_rate": 5.6000000000000006e-05,
26
+ "loss": 1.098,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.16,
31
+ "learning_rate": 7.6e-05,
32
+ "loss": 0.7741,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.2,
37
+ "learning_rate": 9.6e-05,
38
+ "loss": 0.9582,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.24,
43
+ "learning_rate": 0.0001,
44
+ "loss": 1.0714,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.28,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.1548,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.32,
55
+ "learning_rate": 0.0001,
56
+ "loss": 0.8302,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.36,
61
+ "learning_rate": 0.0001,
62
+ "loss": 0.9465,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.4,
67
+ "learning_rate": 0.0001,
68
+ "loss": 0.8649,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.43,
73
+ "learning_rate": 0.0001,
74
+ "loss": 0.8821,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.47,
79
+ "learning_rate": 0.0001,
80
+ "loss": 0.9628,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.51,
85
+ "learning_rate": 0.0001,
86
+ "loss": 0.8706,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.55,
91
+ "learning_rate": 0.0001,
92
+ "loss": 0.669,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.59,
97
+ "learning_rate": 0.0001,
98
+ "loss": 0.6021,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.63,
103
+ "learning_rate": 0.0001,
104
+ "loss": 0.6725,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.67,
109
+ "learning_rate": 0.0001,
110
+ "loss": 0.6651,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.71,
115
+ "learning_rate": 0.0001,
116
+ "loss": 0.7534,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.75,
121
+ "learning_rate": 0.0001,
122
+ "loss": 0.7019,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.79,
127
+ "learning_rate": 0.0001,
128
+ "loss": 0.5879,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.83,
133
+ "learning_rate": 0.0001,
134
+ "loss": 0.5513,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.87,
139
+ "learning_rate": 0.0001,
140
+ "loss": 0.6116,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.91,
145
+ "learning_rate": 0.0001,
146
+ "loss": 0.4817,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.95,
151
+ "learning_rate": 0.0001,
152
+ "loss": 0.6694,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.99,
157
+ "learning_rate": 0.0001,
158
+ "loss": 0.7335,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 1.03,
163
+ "learning_rate": 0.0001,
164
+ "loss": 0.4327,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 1.07,
169
+ "learning_rate": 0.0001,
170
+ "loss": 0.5258,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 1.11,
175
+ "learning_rate": 0.0001,
176
+ "loss": 0.2969,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 1.15,
181
+ "learning_rate": 0.0001,
182
+ "loss": 0.4051,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 1.19,
187
+ "learning_rate": 0.0001,
188
+ "loss": 0.3492,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 1.23,
193
+ "learning_rate": 0.0001,
194
+ "loss": 0.5444,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 1.26,
199
+ "learning_rate": 0.0001,
200
+ "loss": 0.4339,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 1.3,
205
+ "learning_rate": 0.0001,
206
+ "loss": 0.3432,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 1.34,
211
+ "learning_rate": 0.0001,
212
+ "loss": 0.5195,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 1.38,
217
+ "learning_rate": 0.0001,
218
+ "loss": 0.4256,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 1.42,
223
+ "learning_rate": 0.0001,
224
+ "loss": 0.4275,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 1.46,
229
+ "learning_rate": 0.0001,
230
+ "loss": 0.5108,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 1.5,
235
+ "learning_rate": 0.0001,
236
+ "loss": 0.3536,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 1.54,
241
+ "learning_rate": 0.0001,
242
+ "loss": 0.3049,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 1.58,
247
+ "learning_rate": 0.0001,
248
+ "loss": 0.3325,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.62,
253
+ "learning_rate": 0.0001,
254
+ "loss": 0.4221,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 1.66,
259
+ "learning_rate": 0.0001,
260
+ "loss": 0.3514,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 1.7,
265
+ "learning_rate": 0.0001,
266
+ "loss": 0.3613,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 1.74,
271
+ "learning_rate": 0.0001,
272
+ "loss": 0.3535,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 1.78,
277
+ "learning_rate": 0.0001,
278
+ "loss": 0.3633,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.82,
283
+ "learning_rate": 0.0001,
284
+ "loss": 0.3954,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 1.86,
289
+ "learning_rate": 0.0001,
290
+ "loss": 0.288,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 1.9,
295
+ "learning_rate": 0.0001,
296
+ "loss": 0.3639,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 1.94,
301
+ "learning_rate": 0.0001,
302
+ "loss": 0.4876,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 1.98,
307
+ "learning_rate": 0.0001,
308
+ "loss": 0.2981,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 2.02,
313
+ "learning_rate": 0.0001,
314
+ "loss": 0.2474,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 2.06,
319
+ "learning_rate": 0.0001,
320
+ "loss": 0.2725,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 2.09,
325
+ "learning_rate": 0.0001,
326
+ "loss": 0.5512,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 2.13,
331
+ "learning_rate": 0.0001,
332
+ "loss": 0.3865,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 2.17,
337
+ "learning_rate": 0.0001,
338
+ "loss": 0.3104,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 2.21,
343
+ "learning_rate": 0.0001,
344
+ "loss": 0.381,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 2.25,
349
+ "learning_rate": 0.0001,
350
+ "loss": 0.3347,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 2.29,
355
+ "learning_rate": 0.0001,
356
+ "loss": 0.3222,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 2.33,
361
+ "learning_rate": 0.0001,
362
+ "loss": 0.2435,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 2.37,
367
+ "learning_rate": 0.0001,
368
+ "loss": 0.3606,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 2.41,
373
+ "learning_rate": 0.0001,
374
+ "loss": 0.3137,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 2.45,
379
+ "learning_rate": 0.0001,
380
+ "loss": 0.243,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 2.49,
385
+ "learning_rate": 0.0001,
386
+ "loss": 0.4017,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 2.53,
391
+ "learning_rate": 0.0001,
392
+ "loss": 0.3375,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 2.57,
397
+ "learning_rate": 0.0001,
398
+ "loss": 0.2959,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 2.61,
403
+ "learning_rate": 0.0001,
404
+ "loss": 0.31,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 2.65,
409
+ "learning_rate": 0.0001,
410
+ "loss": 0.3298,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 2.69,
415
+ "learning_rate": 0.0001,
416
+ "loss": 0.2462,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 2.73,
421
+ "learning_rate": 0.0001,
422
+ "loss": 0.2599,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 2.77,
427
+ "learning_rate": 0.0001,
428
+ "loss": 0.3736,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 2.81,
433
+ "learning_rate": 0.0001,
434
+ "loss": 0.2408,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 2.85,
439
+ "learning_rate": 0.0001,
440
+ "loss": 0.2684,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 2.89,
445
+ "learning_rate": 0.0001,
446
+ "loss": 0.1603,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 2.92,
451
+ "learning_rate": 0.0001,
452
+ "loss": 0.3044,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 2.96,
457
+ "learning_rate": 0.0001,
458
+ "loss": 0.3166,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 3.0,
463
+ "learning_rate": 0.0001,
464
+ "loss": 0.2564,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 3.04,
469
+ "learning_rate": 0.0001,
470
+ "loss": 0.1702,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 3.08,
475
+ "learning_rate": 0.0001,
476
+ "loss": 0.2165,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 3.12,
481
+ "learning_rate": 0.0001,
482
+ "loss": 0.2071,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 3.16,
487
+ "learning_rate": 0.0001,
488
+ "loss": 0.4326,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 3.2,
493
+ "learning_rate": 0.0001,
494
+ "loss": 0.1978,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 3.24,
499
+ "learning_rate": 0.0001,
500
+ "loss": 0.2628,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 3.28,
505
+ "learning_rate": 0.0001,
506
+ "loss": 0.1515,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 3.32,
511
+ "learning_rate": 0.0001,
512
+ "loss": 0.1968,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 3.36,
517
+ "learning_rate": 0.0001,
518
+ "loss": 0.2305,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 3.4,
523
+ "learning_rate": 0.0001,
524
+ "loss": 0.2085,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 3.44,
529
+ "learning_rate": 0.0001,
530
+ "loss": 0.2006,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 3.48,
535
+ "learning_rate": 0.0001,
536
+ "loss": 0.2685,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 3.52,
541
+ "learning_rate": 0.0001,
542
+ "loss": 0.192,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 3.56,
547
+ "learning_rate": 0.0001,
548
+ "loss": 0.1993,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 3.6,
553
+ "learning_rate": 0.0001,
554
+ "loss": 0.1312,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 3.64,
559
+ "learning_rate": 0.0001,
560
+ "loss": 0.2326,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 3.68,
565
+ "learning_rate": 0.0001,
566
+ "loss": 0.2676,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 3.72,
571
+ "learning_rate": 0.0001,
572
+ "loss": 0.2519,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 3.75,
577
+ "learning_rate": 0.0001,
578
+ "loss": 0.1722,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 3.79,
583
+ "learning_rate": 0.0001,
584
+ "loss": 0.1649,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 3.83,
589
+ "learning_rate": 0.0001,
590
+ "loss": 0.1923,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 3.87,
595
+ "learning_rate": 0.0001,
596
+ "loss": 0.3485,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 3.91,
601
+ "learning_rate": 0.0001,
602
+ "loss": 0.15,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 3.95,
607
+ "learning_rate": 0.0001,
608
+ "loss": 0.258,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 3.95,
613
+ "step": 1000,
614
+ "total_flos": 5.6524204199809e+19,
615
+ "train_loss": 0.4612073403596878,
616
+ "train_runtime": 4968.0781,
617
+ "train_samples_per_second": 6.441,
618
+ "train_steps_per_second": 0.201
619
+ }
620
+ ],
621
+ "logging_steps": 10,
622
+ "max_steps": 1000,
623
+ "num_input_tokens_seen": 0,
624
+ "num_train_epochs": 4,
625
+ "save_steps": 1000,
626
+ "total_flos": 5.6524204199809e+19,
627
+ "train_batch_size": 32,
628
+ "trial_name": null,
629
+ "trial_params": null
630
+ }